Python Bill.add_action方法代码示例

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def scrape2009(self, url, year, chamberName, session, number):
        "e.g. http://www.legis.ga.gov/legis/2009_10/sum/sb1.htm"
        page = parse(url).getroot()

        # Bill
        try:
            name = page.cssselect("#legislation h1")[0].text_content().strip()
        except:
            name = "Unknown"
        bill = Bill(session, chamberName, number, name)

        # Sponsorships
        for a in page.cssselect("#sponsors a"):
            bill.add_sponsor("", a.text_content().strip())

        self.parse_votes(url, page, chamberName, bill)

        # Actions
        for row in page.cssselect("#history tr")[1:]:
            date = row[0].text_content().strip()
            action_text = row[1].text_content().strip()

            if "/" not in date:
                continue

            if action_text.startswith("Senate"):
                bill.add_action("upper", action_text, date)
            elif action_text.startswith("House"):
                bill.add_action("lower", action_text, date)

        # Versions
        for row in page.cssselect("#versions a"):
            bill.add_version(a.text_content(), urlparse.urljoin(url, a.get("href")))

        self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def scrape2009(self, url, year, chamberName, session, number):
        "e.g. http://www.legis.ga.gov/legis/2009_10/sum/sum/sb1.htm"
        page = parse(url).getroot()

        # Bill
        name = page.cssselect('#legislation h1')[0].text_content().strip()
        bill = Bill(session, chamberName, number, name)

        # Sponsorships
        for a in page.cssselect("#sponsors a"):
            bill.add_sponsor('', a.text_content().strip())

        # Actions
        for row in page.cssselect('#history tr')[1:]:
            date = row[0].text_content().strip()
            action_text = row[1].text_content().strip()

            if '/' not in date:
                continue

            if action_text.startswith('Senate'):
                bill.add_action('upper', action_text, date)
            elif action_text.startswith('House'):
                bill.add_action('lower', action_text, date)

        # Versions
        for row in page.cssselect('#versions a'):
            bill.add_version(a.text_content(),
                             urlparse.urljoin(url, a.get('href')))

        self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def scrape1999(self, url, year, chamberName, session, number):
        "e.g. http://www.legis.ga.gov/legis/1999_00/leg/sum/sb1.htm"
        page = parse(url).getroot()

        # Grab the interesting tables on the page.
        tables = page.cssselect("table")

        # Bill
        name = tables[1].cssselect("a")[0].text_content().split("-", 1)[1]
        bill = Bill(session, chamberName, number, name)

        # Versions
        bill.add_version("Current", url.replace("/sum/", "/fulltext/"))

        # Sponsorships
        for a in tables[2].cssselect("a"):
            bill.add_sponsor("", a.text_content().strip())

        self.parse_votes_1999(url, page, chamberName, bill)

        # Actions
        for row in tables[-1].cssselect("tr"):
            senate_date = row[0].text_content().strip()
            action_text = row[1].text_content().strip()
            house_date = row[2].text_content().strip()
            if "/" not in senate_date and "/" not in house_date:
                continue
            if senate_date:
                bill.add_action("upper", action_text, senate_date)
            if house_date:
                bill.add_action("lower", action_text, house_date)

        self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def scrape2003(self, url, year, chamberName, session, number):
        "e.g. http://www.legis.ga.gov/legis/2003_04/sum/sb1.htm"
        page = parse(url).getroot()

        # Grab the interesting tables on the page.
        tables = page.cssselect("center table")

        # Bill
        name = tables[0].text_content().split("-", 1)[1]
        bill = Bill(session, chamberName, number, name)

        # Sponsorships
        for a in tables[1].cssselect("a"):
            bill.add_sponsor("", a.text_content().strip())

        self.parse_votes_2001_2004(url, page, chamberName, bill)

        # Actions
        center = page.cssselect("center table center")[0]

        for row in center.cssselect("table")[-2].cssselect("tr")[2:]:
            date = row[0].text_content().strip()
            action_text = row[1].text_content().strip()
            if "/" not in date:
                continue
            if action_text.startswith("Senate"):
                bill.add_action("upper", action_text, date)
            elif action_text.startswith("House"):
                bill.add_action("lower", action_text, date)

        # Versions
        for row in center.cssselect("table")[-1].cssselect("a"):
            bill.add_version(a.text_content(), urlparse.urljoin(url, a.get("href")))

        self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def scrape2003(self, url, year, chamberName, session, number):
        "e.g. http://www.legis.ga.gov/legis/2003_04/sum/sum/sb1.htm"
        page = parse(url).getroot()

        # Grab the interesting tables on the page.
        tables = page.cssselect('center table')

        # Bill
        name = tables[0].text_content().split('-', 1)[1]
        bill = Bill(session, chamberName, number, name)

        # Sponsorships
        for a in tables[1].cssselect('a'):
            bill.add_sponsor('', a.text_content().strip())

        # Actions
        center = page.cssselect('center table center')[0]

        for row in center.cssselect('table')[-2].cssselect('tr')[2:]:
            date = row[0].text_content().strip()
            action_text = row[1].text_content().strip()
            if '/' not in date:
                continue
            if action_text.startswith('Senate'):
                bill.add_action('upper', action_text, date)
            elif action_text.startswith('House'):
                bill.add_action('lower', action_text, date)

        # Versions
        for row in center.cssselect('table')[-1].cssselect('a'):
            bill.add_version(a.text_content(),
                             urlparse.urljoin(url, a.get('href')))

        self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def scrape1999(self, url, year, chamberName, session, number):
        "e.g. http://www.legis.ga.gov/legis/1999_00/leg/sum/sb1.htm"
        page = parse(url).getroot()

        # Grab the interesting tables on the page.
        tables = page.cssselect('table')

        # Bill
        name = tables[1].cssselect('a')[0].text_content().split('-', 1)[1]
        bill = Bill(session, chamberName, number, name)

        # Versions
        bill.add_version('Current', url.replace('/sum/', '/fulltext/'))

        # Sponsorships
        for a in tables[2].cssselect('a'):
            bill.add_sponsor('', a.text_content().strip())

        # Actions
        for row in tables[-1].cssselect('tr'):
            senate_date = row[0].text_content().strip()
            action_text = row[1].text_content().strip()
            house_date = row[2].text_content().strip()
            if '/' not in senate_date and '/' not in house_date:
                continue
            if senate_date:
                bill.add_action('upper', action_text, senate_date)
            if house_date:
                bill.add_action('lower', action_text, house_date)

        self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def get_bill_info(self, chamber, session, bill_detail_url):
	"""Extracts all the requested info for a given bill.  
	
	Calls the parent's methods to enter the results into CSV files.
	"""
        bill_detail_url_base='https://www.revisor.leg.state.mn.us/revisor/pages/search_status/'
        bill_detail_url = urlparse.urljoin(bill_detail_url_base, bill_detail_url)

        if chamber == "House":
            chamber = 'lower'
        else:
            chamber = 'upper'

        with self.soup_context(bill_detail_url) as bill_soup:

            bill_id = self.extract_bill_id(bill_soup)
            bill_title =  self.extract_bill_title(bill_soup)
            bill = Bill(session, chamber, bill_id, bill_title)

            # get all versions of the bill.
            # Versions of a bill are on a separate page, linked to from the bill
            # details page in a link titled, "Bill Text".
            version_url_base = 'https://www.revisor.leg.state.mn.us'
            bill_version_link = self.extract_bill_version_link(bill_soup)

        version_detail_url = urlparse.urljoin(version_url_base, bill_version_link)

        with self.soup_context(version_detail_url) as version_soup:

            # MN bills can have multiple versions.  Get them all, and loop over
            # the results, adding each one.
            bill_versions = self.extract_bill_versions(version_soup)
            for version in bill_versions:
                version_name = version['name']
                version_url = urlparse.urljoin(version_url_base, version['url'])
                bill.add_version(version_name, version_url)

            # grab primary and cosponsors 
            # MN uses "Primary Author" to name a bill's primary sponsor.
            # Everyone else listed will be added as a 'cosponsor'.
            sponsors = self.extract_bill_sponsors(bill_soup)
            primary_sponsor = sponsors[0]
            cosponsors = sponsors[1:]
            bill.add_sponsor('primary', primary_sponsor)
            for leg in cosponsors:
                bill.add_sponsor('cosponsor', leg)

            # Add Actions performed on the bill.
            bill_actions = self.extract_bill_actions(bill_soup, chamber)
            for action in bill_actions:
                action_chamber = action['action_chamber']
                action_date = action['action_date']
                action_text = action['action_text']
                bill.add_action(action_chamber, action_text, action_date)

        self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def scrape_bill(self, chamber, session, billid, histurl, year):
        if year[0] != 'R':
            session = year
        else:
            session = self.metadata['session_details'][year][
                'sub_sessions'][int(year[0]) - 1]

        with self.urlopen_context(histurl) as data:
            soup = BS(cleansource(data))
            basicinfo = soup.findAll('div', id='bhistleft')[0]
            hist = basicinfo.table

            sponsor = None
            title = None
            for b in basicinfo.findAll('b'):
                if b.next.startswith('SUMMARY'):
                    title = b.findNextSiblings(text=True)[0].strip()
                elif b.next.startswith('SPONSOR'):
                    for a in b.findNextSiblings('a'):
                        if not issponsorlink(a):
                            break
                        sponsor = cleansponsor(a.contents[0])

            bill = Bill(session, chamber, billid, title)

            if sponsor:
                bill.add_sponsor('primary', sponsor)

            for row in hist.findAll('tr'):
                link = row.td.a
                vlink = urlbase % link['href']
                vname = link.contents[0].strip()
                bill.add_version(vname, vlink)

            history = soup.findAll('div', id='bhisttab')[0].table
            rows = history.findAll('tr')[1:]
            for row in rows:
                tds = row.findAll('td')
                if len(tds) < 2:
                    # This is not actually an action
                    continue
                date, action = row.findAll('td')[:2]
                date = dt.datetime.strptime(date.contents[0], '%m/%d/%y')
                action = action.contents[0].strip()
                if 'House' in action:
                    actor = 'lower'
                elif 'Senate' in action:
                    actor = 'upper'
                else:  # for lack of a better
                    actor = chamber

                bill.add_action(actor, action, date)

        self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def parse_bill(self, chamber, session, bill_id, bill_info_url):
        with self.urlopen_context(bill_info_url) as bill_info_data:
            bill_info = self.soup_parser(bill_info_data)
            version_url = '%s/bill.doc' % bill_id
            version_link = bill_info.find(href=version_url)

            if not version_link:
                # This bill was withdrawn
                return

            bill_title = version_link.findNext('p').contents[0].strip()

            bill = Bill(session, chamber, bill_id, bill_title)
            bill.add_version("Most Recent Version",
                             session_url(session) + version_url)
            bill.add_source(bill_info_url)

            sponsor_links = bill_info.findAll(href=re.compile(
                    'legislator/[SH]\d+\.htm'))

            for sponsor_link in sponsor_links:
                bill.add_sponsor('primary', sponsor_link.contents[0].strip())

            action_p = version_link.findAllNext('p')[-1]
            for action in action_p.findAll(text=True):
                action = action.strip()
                if (not action or action == 'last action' or
                    'Prefiled' in action):
                    continue

                action_date = action.split('-')[0]
                action_date = dt.datetime.strptime(action_date, '%b %d')
                # Fix:
                action_date = action_date.replace(
                    year=int('20' + session[2:4]))

                action = '-'.join(action.split('-')[1:])

                if action.endswith('House') or action.endswith('(H)'):
                    actor = 'lower'
                elif action.endswith('Senate') or action.endswith('(S)'):
                    actor = 'upper'
                else:
                    actor = chamber

                bill.add_action(actor, action, action_date)

            vote_link = bill_info.find(href=re.compile('.*/vote_history.pdf'))
            if vote_link:
                bill.add_document(
                    'vote_history.pdf',
                    bill_info_url.replace('.htm', '') + "/vote_history.pdf")

            self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def get_bill_info(self, chamber, session, bill_detail_url, version_list_url):
	"""Extracts all the requested info for a given bill.

	Calls the parent's methods to enter the results into JSON files.
	"""
        if chamber == "House":
            chamber = 'lower'
        else:
            chamber = 'upper'

        with self.soup_context(bill_detail_url) as bill_soup:

            bill_id = self.extract_bill_id(bill_soup)
            bill_title =  self.extract_bill_title(bill_soup)
            bill = Bill(session, chamber, bill_id, bill_title)

        # Get all versions of the bill.
        # Versions of a bill are on a separate page, linked to from the column
        # labeled, "Bill Text", on the search results page.

        with self.soup_context(version_list_url) as version_soup:

            # MN bills can have multiple versions.  Get them all, and loop over
            # the results, adding each one.
            self.debug("Extracting bill versions from: " + version_list_url)
            bill_versions = self.extract_bill_versions(version_soup)
            for version in bill_versions:
                version_name = version['name']
                version_url = urlparse.urljoin(VERSION_URL_BASE, version['url'])
                bill.add_version(version_name, version_url)

            # grab primary and cosponsors
            # MN uses "Primary Author" to name a bill's primary sponsor.
            # Everyone else listed will be added as a 'cosponsor'.
            sponsors = self.extract_bill_sponsors(bill_soup)
            primary_sponsor = sponsors[0]
            cosponsors = sponsors[1:]
            bill.add_sponsor('primary', primary_sponsor)
            for leg in cosponsors:
                bill.add_sponsor('cosponsor', leg)

            # Add Actions performed on the bill.
            bill_actions = self.extract_bill_actions(bill_soup, chamber)
            for action in bill_actions:
                action_chamber = action['action_chamber']
                action_date = action['action_date']
                action_text = action['action_text']
                bill.add_action(action_chamber, action_text, action_date)

        self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def scrape1995(self, url, year, chamberName, session, number):
        "e.g. http://www.legis.ga.gov/legis/1995_96/leg/sum/sb1.htm"
        page = parse(url).getroot()

        # Bill
        name = page.cssselect('h3 br')[0].tail.split('-', 1)[1].strip()
        bill = Bill(session, chamberName, number, name)

        # Versions
        bill.add_version('Current', url.replace('/sum/', '/fulltext/'))

        # Sponsorships
        rows = page.cssselect('center table tr')
        for row in rows:
            if row.text_content().strip() == 'Sponsor and CoSponsors':
                continue
            if row.text_content().strip() == 'Links / Committees / Status':
                break
            for a in row.cssselect('a'):
                bill.add_sponsor('', a.text_content().strip())

        # Actions
        # The actions are in a pre table that looks like:
        """    SENATE                         HOUSE
               -------------------------------------
             1/13/95   Read 1st time          2/6/95
             1/31/95   Favorably Reported
             2/1/95    Read 2nd Time          2/7/95
             2/3/95    Read 3rd Time
             2/3/95    Passed/Adopted                   """

        actions = page.cssselect('pre')[0].text_content().split('\n')
        actions = actions[2:]
        for action in actions:
            senate_date = action[:22].strip()
            action_text = action[23:46].strip()
            house_date = action[46:].strip()

            if '/' not in senate_date and '/' not in house_date:
                continue

            if senate_date:
                bill.add_action('upper', action_text, senate_date)

            if house_date:
                bill.add_action('lower', action_text, house_date)

        self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def scrape1995(self, url, year, chamberName, session, number):
        "e.g. http://www.legis.ga.gov/legis/1995_96/leg/sum/sb1.htm"
        page = parse(url).getroot()

        # Bill
        name = page.cssselect("h3 br")[0].tail.split("-", 1)[1].strip()
        bill = Bill(session, chamberName, number, name)

        # Versions
        bill.add_version("Current", url.replace("/sum/", "/fulltext/"))

        # Sponsorships
        rows = page.cssselect("center table tr")
        for row in rows:
            if row.text_content().strip() == "Sponsor and CoSponsors":
                continue
            if row.text_content().strip() == "Links / Committees / Status":
                break
            for a in row.cssselect("a"):
                bill.add_sponsor("", a.text_content().strip())

        # Actions
        # The actions are in a pre table that looks like:
        """    SENATE                         HOUSE
               -------------------------------------
             1/13/95   Read 1st time          2/6/95
             1/31/95   Favorably Reported
             2/1/95    Read 2nd Time          2/7/95
             2/3/95    Read 3rd Time
             2/3/95    Passed/Adopted                   """

        actions = page.cssselect("pre")[0].text_content().split("\n")
        actions = actions[2:]
        for action in actions:
            senate_date = action[:22].strip()
            action_text = action[23:46].strip()
            house_date = action[46:].strip()

            if "/" not in senate_date and "/" not in house_date:
                continue

            if senate_date:
                bill.add_action("upper", action_text, senate_date)

            if house_date:
                bill.add_action("lower", action_text, house_date)

        self.add_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def parse_bill(self, chamber, session, bill_id, bill_info_url):
        with self.urlopen_context(bill_info_url) as bill_info_data:
            bill_info = self.soup_parser(bill_info_data)
            version_url = "%s/bill.doc" % bill_id
            version_link = bill_info.find(href=version_url)

            if not version_link:
                # This bill was withdrawn
                return

            bill_title = version_link.findNext("p").contents[0].strip()

            bill = Bill(session, chamber, bill_id, bill_title)
            bill.add_version("Most Recent Version", session_url(session) + version_url)
            bill.add_source(bill_info_url)

            sponsor_links = bill_info.findAll(href=re.compile("legislator/[SH]\d+\.htm"))

            for sponsor_link in sponsor_links:
                bill.add_sponsor("primary", sponsor_link.contents[0].strip())

            action_p = version_link.findAllNext("p")[-1]
            for action in action_p.findAll(text=True):
                action = action.strip()
                if not action or action == "last action" or "Prefiled" in action:
                    continue

                action_date = action.split("-")[0]
                action_date = dt.datetime.strptime(action_date, "%b %d")
                # Fix:
                action_date = action_date.replace(year=int("20" + session[2:4]))

                action = "-".join(action.split("-")[1:])

                if action.endswith("House") or action.endswith("(H)"):
                    actor = "lower"
                elif action.endswith("Senate") or action.endswith("(S)"):
                    actor = "upper"
                else:
                    actor = chamber

                bill.add_action(actor, action, action_date)

            vote_link = bill_info.find(href=re.compile(".*/vote_history.pdf"))
            if vote_link:
                bill.add_document("vote_history.pdf", bill_info_url.replace(".htm", "") + "/vote_history.pdf")

            self.save_bill(bill)

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
    def parse_bill_xml(self, chamber, session, txt):
        root = lxml.etree.fromstring(txt)
        bill_id = ' '.join(root.attrib['bill'].split(' ')[1:])
        bill_title = root.findtext("caption")

        if session[2] == 'R':
            session = session[0:2]

        bill = Bill(session, chamber, bill_id, bill_title)

        for action in root.findall('actions/action'):
            act_date = dt.datetime.strptime(action.findtext('date'),
                                            "%m/%d/%Y")

            extra = {}
            extra['action_number'] = action.find('actionNumber').text
            comment = action.find('comment')
            if comment is not None and comment.text:
                extra['comment'] = comment.text.strip()

            actor = {'H': 'lower',
                     'S': 'upper',
                     'E': 'executive'}[extra['action_number'][0]]

            bill.add_action(actor, action.findtext('description'),
                            act_date, **extra)

        for author in root.findtext('authors').split(' | '):
            if author != "":
                bill.add_sponsor('author', author)
        for coauthor in root.findtext('coauthors').split(' | '):
            if coauthor != "":
                bill.add_sponsor('coauthor', coauthor)
        for sponsor in root.findtext('sponsors').split(' | '):
            if sponsor != "":
                bill.add_sponsor('sponsor', sponsor)
        for cosponsor in root.findtext('cosponsors').split(' | '):
            if cosponsor != "":
                bill.add_sponsor('cosponsor', cosponsor)

        bill['subjects'] = []
        for subject in root.iterfind('subjects/subject'):
            bill['subjects'].append(subject.text.strip())

        return bill

# 需要导入模块: from pyutils.legislation import Bill [as 别名]
# 或者: from pyutils.legislation.Bill import add_action [as 别名]
def parse_bill(scraper, url):
    """Given a bill status URL, return a fully loaded Bill object, except for votes, which
       are expected to be handled externally.
    """
    session = extract_session(url)
    chamber = chamber_for_doctype(extract_doctype(url))
    s = get_soup(scraper, url)
    bill_id = extract_bill_id(s)
    landmark = s(text=re.compile(".*Short Description.*"))
    name_span = landmark[0].findParent().findNextSibling()
    bill_name = get_text(name_span)
    bill = Bill(session, chamber, bill_id, bill_name.strip(),status_url=url)
    actions = extract_actions(s)
    for chamber,action,date in actions:
        bill.add_action(chamber,action,date) #kwargs are permitted if we have 'em.  
    sponsor_dict = extract_sponsors_from_actions([action[1] for action in actions])
    for type,namelist in sponsor_dict.iteritems():
        for name in namelist:
            bill.add_sponsor(type,name)
    for name,link in extract_versions(scraper, s):
        bill.add_version(name,link)
    return bill